Generating graphical user interfaces comprising dynamic credit value user interface elements determined from a credit value model

Abstract

The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that utilize a machine learning model and a credit value model to generate user interface elements that present credit values and credit value conditions in real time for user accounts. For instance, the disclosed systems can generate an activity score using an activity machine learning model with internal user activity data of a user account. Then, utilizing a credit value model with the activity score and a user activity condition, the disclosed systems can determine a dynamic credit value range for the user account. Indeed, the disclosed systems can display user interface elements with selectable credit values from the dynamic credit value range. Additionally, the disclosed systems can utilize the credit value model to determine and display one or more dynamic credit value conditions for a selected credit value received from the selectable credit values.

What is claimed is: 
     
       1. A computer-implemented method comprising:
 selecting an activity machine learning model from a plurality of activity machine learning models based on a user activity duration corresponding to a user account, wherein:
 the plurality of activity machine learning models are trained based on historical transaction activity to predict activity scores corresponding to user classes having different user activity durations, and 
 the plurality of activity machine learning models comprise neural networks or decision tree models; 
 
 generating an activity score utilizing the activity machine learning model from internal user activity data corresponding to the user account; 
 determining, utilizing a credit value model, a credit value range and one or more credit value conditions from the activity score; and 
 providing, for display via a computing device corresponding to the user account, credit values from the credit value range and the one or more credit value conditions. 
 
     
     
       2. The computer-implemented method of  claim 1 , further comprising determining, utilizing the credit value model, the credit value range from the activity score generated from the activity machine learning model and a user activity condition corresponding to the user account. 
     
     
       3. The computer-implemented method of  claim 1 , further comprising:
 identifying an additional user account corresponding to an additional user activity duration; and 
 selecting an additional activity machine learning model from the plurality of activity machine learning models based on the additional user activity duration corresponding to the additional user account. 
 
     
     
       4. The computer-implemented method of  claim 3 , further comprising generating an additional activity score utilizing the additional activity machine learning model from additional internal user activity data corresponding to the additional user account. 
     
     
       5. The computer-implemented method of  claim 4 , further comprising:
 determining, utilizing the credit value model, an additional credit value range and at least one credit value condition from the additional activity score; and 
 providing for display via an additional computing device corresponding to the additional user account, additional credit values from the credit value range and the at least one credit value condition. 
 
     
     
       6. The computer-implemented method of  claim 1 , wherein generating the activity score comprises utilizing the activity machine learning model to generate the activity score from at least one of: historical application utilization or a duration of satisfying a threshold account value. 
     
     
       7. The computer-implemented method of  claim 1 , wherein determining the credit value range and the one or more credit value conditions from the activity score comprises determining, from an offer category matrix, an offer category for the user account utilizing a combination of the activity score and a user activity condition corresponding to the user account, wherein the offer category matrix maps activity scores and user activity conditions to one or more offer categories. 
     
     
       8. The computer-implemented method of  claim 7 , wherein determining the credit value range and the one or more credit value conditions from the activity score comprises determining the credit value range by identifying one or more credit values that correspond to the offer category within a credit value matrix, wherein the credit value matrix comprises a mapping between offer categories and dynamic credit values. 
     
     
       9. The computer-implemented method of  claim 8 , further comprising determining the offer category utilizing the offer category matrix by identifying an offer category within the offer category matrix that maps to the activity score and the user activity condition corresponding to the user account. 
     
     
       10. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:
 select an activity machine learning model from a plurality of activity machine learning models based on a user activity duration corresponding to a user account, wherein:
 the plurality of activity machine learning models are trained based on historical transaction activity to predict activity scores corresponding to user classes having different user activity durations, and 
 the plurality of activity machine learning models comprise neural networks or decision tree models; 
 
 generate an activity score utilizing the activity machine learning model from internal user activity data corresponding to the user account; 
 determine, utilizing a credit value model, a credit value range and one or more credit value conditions from the activity score; and 
 provide, for display via a computing device corresponding to the user account, credit values from the credit value range and the one or more credit value conditions. 
 
     
     
       11. The non-transitory computer-readable medium of  claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to determine, utilizing the credit value model, the credit value range from the activity score generated from the activity machine learning model and a user activity condition corresponding to the user account. 
     
     
       12. The non-transitory computer-readable medium of  claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
 identify an additional user account corresponding to an additional user activity duration; and 
 select an additional activity machine learning model from the plurality of activity machine learning models based on the additional user activity duration corresponding to the additional user account. 
 
     
     
       13. The non-transitory computer-readable medium of  claim 12 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate an additional activity score utilizing the additional activity machine learning model from additional internal user activity data corresponding to the additional user account. 
     
     
       14. The non-transitory computer-readable medium of  claim 13 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
 determine, utilizing the credit value model, an additional credit value range and at least one credit value condition from the additional activity score; and 
 provide for display via an additional computing device corresponding to the additional user account, additional credit values from the credit value range and the at least one credit value condition. 
 
     
     
       15. The non-transitory computer-readable medium of  claim 10 , wherein generating the activity score comprises utilizing the activity machine learning model to generate the activity score from at least one of: historical application utilization or a duration of satisfying a threshold account value. 
     
     
       16. A system comprising:
 at least one processor; and 
 at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to: 
 select an activity machine learning model from a plurality of activity machine learning models based on a user activity duration corresponding to a user account, wherein:
 the plurality of activity machine learning models are trained based on historical transaction activity to predict activity scores corresponding to user classes having different user activity durations, and 
 the plurality of activity machine learning models comprise neural networks or decision tree models; 
 
 generate an activity score utilizing the activity machine learning model from internal user activity data corresponding to the user account; 
 determine, utilizing a credit value model, a credit value range and one or more credit value conditions from the activity score; and 
 provide, for display via a computing device corresponding to the user account, credit values from the credit value range and the one or more credit value conditions. 
 
     
     
       17. The system of  claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to determine, utilizing the credit value model, the credit value range from the activity score generated from the activity machine learning model and a user activity condition corresponding to the user account. 
     
     
       18. The system of  claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
 identify an additional user account corresponding to an additional user activity duration; and 
 select an additional activity machine learning model from the plurality of activity machine learning models based on the additional user activity duration corresponding to the additional user account. 
 
     
     
       19. The system of  claim 18 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate an additional activity score utilizing the additional activity machine learning model from additional internal user activity data corresponding to the additional user account. 
     
     
       20. The system of  claim 19 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
 determine, utilizing the credit value model, an additional credit value range and at least one credit value condition from the additional activity score; and 
 provide for display via an additional computing device corresponding to the additional user account, additional credit values from the credit value range and the at least one credit value condition.